{
  "profile": "v620-w8-tp4-mtp0",
  "image": "sha256:4f2d919ceed2b8b21cfd4d13661d83d197fbdddcc82e5a799dc4689c8c407794",
  "container": "86d58c7ae420738f87e752aacaf340b66c6c2aaf59dc74b10e8688076ccb84d4",
  "model_load_report_rank": 0,
  "retest_logged_model_load_delta_GiB": 13.55,
  "retest_logged_model_load_seconds": 69.213373,
  "retest_logged_available_KV_GiB": 13.67,
  "retest_explicit_KV_budget_bytes": null,
  "retest_KV_budget_GiB": 13.67,
  "retest_KV_budget_scope": "Automatic available-memory report; rounded",
  "retest_logged_GPU_KV_tokens": 223440,
  "retest_logged_context_capacity_x": 6.68,
  "retest_logged_context_tokens": 131072,
  "source_log": "retest-evidence/v620-w8-tp4-mtp0/service-final.log",
  "source_log_sha256": "726feb8d07ee3d1196f5ae64c801549b862215683eec091a52bf1c101766150e",
  "sealed_index_sha256": "24a7a4434d6a3c8345a672f0f4aba71a5b4211d8aaa88c3563efe7c930366fab",
  "source_lines": {
    "model_load": {
      "line": 120,
      "text": "(Worker pid=83) (Worker_TP0 pid=83) INFO 10-26 17:51:30 [gpu_model_runner.py:4579] Model loading took 13.55 GiB memory and 69.213373 seconds"
    },
    "automatic_KV_budget": {
      "line": 139,
      "text": "(Worker pid=83) (Worker_TP0 pid=83) INFO 10-26 17:55:28 [gpu_worker.py:453] Available KV cache memory: 13.67 GiB"
    },
    "grouped_KV_tokens": {
      "line": 145,
      "text": "(EngineCore_DP0 pid=65) INFO 10-26 17:55:29 [kv_cache_utils.py:1314] GPU KV cache size: 223,440 tokens"
    },
    "context_capacity": {
      "line": 146,
      "text": "(EngineCore_DP0 pid=65) INFO 10-26 17:55:29 [kv_cache_utils.py:1319] Maximum concurrency for 131,072 tokens per request: 6.68x"
    }
  },
  "limits": "Model-load delta and automatic available-KV values are rounded engine reports, not measured physical VRAM or exact tensor-byte totals. Explicit budgets are configuration values confirmed in the loaded engine, not profiled availability. Grouped KV tokens and concurrency use the engine hybrid-cache accounting; they are not proof of a completed full-context request or an exact request ceiling."
}
